setwd(“~/Documents/2016Spring/260/final”)

load library

#rm(list=ls())
library(knitr)
opts_chunk$set(cache = TRUE, message = FALSE)
library(knitr)
library(readr)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyr)
library(stringr)
library(ggplot2)
library(gridExtra)

## 
## Attaching package: 'gridExtra'

## The following object is masked from 'package:dplyr':
## 
##     combine

library(graphics)
library(plotrix)
library(gridBase)
library(grid)
theme_set(theme_bw(base_size = 16))

read data

#raw<-read.csv("tidy_minions.csv",header=TRUE,sep="\t")
load("minions_text.RData")
data<-minions_text

distribution of Cost

#remove costs that are "12" and "20" 
Cost<-data%>%arrange(cost)
Cost<-unique(data%>%filter(cost<=10)%>%group_by(cost)%>%mutate(n=n())%>%ungroup()%>%select(cost,n))
lbls<-Cost$cost
slices<-Cost$n
pct <- round(slices/sum(slices)*100)
lbls <- paste(lbls, pct) # add percents to labels 
lbls <- paste(lbls,"%",sep="") # ad % to labels 
pie(slices,labels = lbls, col=rainbow(length(lbls)),
    main="Pie Chart of Card Cost")

Conclusion: cards with cost “2”,“3”,“4” out of the 11 possible costs occupying around 54% in total are most common in the deck

distribution of attack

#pie chart
Attackk<-data%>%arrange(attack)
Attack<-unique(Attackk%>%group_by(attack)%>%mutate(n=n())%>%ungroup()%>%select(attack,n))
lbls<-Attack$attack
slices<-Attack$n
pct <- round(slices/sum(slices)*100)
lbls <- paste(lbls, pct) # add percents to labels 
lbls <- paste(lbls,"%",sep="") # ad % to labels 
pie(slices,labels = lbls, col=rainbow(length(lbls)),
    main="Pie Chart of Attack")

#histogram
x <- Attackk$attack
h<-hist(x, breaks=12, col="red", ylim=c(0,120),xlab="deal damage to the opponent", 
    main="Histogram for attack") 
xfit<-seq(min(x),max(x),length=40) 
yfit<-dnorm(xfit,mean=mean(x),sd=sd(x)) 
yfit <- yfit*diff(h$mids[1:2])*length(x) 
lines(xfit, yfit, col="blue", lwd=2)

#density plot
d <- density(Attackk$attack)
plot(d, main="Kernel density for attack")
polygon(d, col="red", border="blue")

distribution of health

#pie chart
Health<-data%>%arrange(health)
Health<-unique(Health%>%group_by(health)%>%mutate(n=n())%>%ungroup()%>%select(health,n))
lbls<-Health$health
slices<-Health$n
pct <- round(slices/sum(slices)*100)
lbls <- paste(lbls, pct) # add percents to labels 
lbls <- paste(lbls,"%",sep="") # ad % to labels 
pie(slices,labels = lbls, col=rainbow(length(lbls)),
    main="Pie Chart of Health")

#histogram
x <- Health$health
h<-hist(x, breaks=12, col="green", xlab="Health for each card", 
    main="Histogram for card health") 
xfit<-seq(min(x),max(x),length=40) 
yfit<-dnorm(xfit,mean=mean(x),sd=sd(x)) 
yfit <- yfit*diff(h$mids[1:2])*length(x) 
lines(xfit, yfit, col="blue", lwd=2)

distribution of mechanics

#pie chart
Mechanics<-data%>%arrange(mechanics)
Mechanics<-unique(Mechanics%>%group_by(mechanics)%>%mutate(n=n())%>%ungroup()%>%select(mechanics,n))
lbls<-Mechanics$mechanics
slices<-Health$n
pct <- round(slices/sum(slices)*100)
lbls <- paste(lbls, pct) # add percents to labels 
lbls <- paste(lbls,"%",sep="") # ad % to labels 
pie(slices,labels = lbls, col=rainbow(length(lbls)),
    main="Pie Chart of Mechanics")

#histogram
meme<-barplot(prop.table(table(data$mechanics)),col=rainbow(20), names.arg="")
## Use grid to add the labels    
vps <- baseViewports()
pushViewport(vps$inner, vps$figure, vps$plot)

grid.text(Mechanics$mechanics,x = unit(meme, "native"), y=unit(-1, "lines"),
    just="right", rot=50)

popViewport(3)

distribution of playerclass

#pie chart
pc<-data%>%arrange(playerClass)
pc<-unique(pc%>%group_by(playerClass)%>%mutate(n=n())%>%ungroup()%>%select(playerClass,n))
lbls<-pc$playerClass
slices<-pc$n
pct <- round(slices/sum(slices)*100)
lbls <- paste(lbls, pct) # add percents to labels 
lbls <- paste(lbls,"%",sep="") # ad % to labels 
pie(slices,labels = lbls, col=rainbow(length(lbls)),
    main="Pie Chart of player class")

#histogram
pcpc<-barplot(prop.table(table(data$playerClass)),col=rainbow(28), names.arg="")
## Use grid to add the labels    
vps <- baseViewports()
pushViewport(vps$inner, vps$figure, vps$plot)

grid.text(pc$playerClass,x = unit(meme, "native"),y=unit(-1, "lines"),rot=50)

popViewport(3)

distribution of cardSet

#pie chart
cs<-data%>%arrange(cardSet)
cs<-unique(cs%>%group_by(cardSet)%>%mutate(n=n())%>%ungroup()%>%select(cardSet,n))
lbls<-cs$cardSet
slices<-cs$n
pct <- round(slices/sum(slices)*100)
lbls <- paste(lbls, pct) # add percents to labels 
lbls <- paste(lbls,"%",sep="") # ad % to labels 
pie(slices,labels = lbls, col=rainbow(length(lbls)),
    main="Pie Chart of card set")

#histogram
cscs<-barplot(prop.table(table(data$cardSet)),col=rainbow(10), names.arg="")
## Use grid to add the labels    
vps <- baseViewports()
pushViewport(vps$inner, vps$figure, vps$plot)

grid.text(cs$cardSet,x = unit(meme, "native"),y=unit(-1, "lines"),rot=50)

popViewport(3)

distribution of rarity

#pie chart
rr<-unique(data%>%group_by(rarity)%>%mutate(n=n())%>%ungroup()%>%select(rarity,n))
lbls<-rr$rarity
slices<-rr$n
pct <- round(slices/sum(slices)*100)
lbls <- paste(lbls, pct) # add percents to labels 
lbls <- paste(lbls,"%",sep="") # ad % to labels 
pie(slices,labels = lbls, col=rainbow(length(lbls)),
    main="Pie Chart of rarity")

#histogram
rrrr<-barplot(prop.table(table(data$rarity)),col=rainbow(10), names.arg="")
## Use grid to add the labels    
vps <- baseViewports()
pushViewport(vps$inner, vps$figure, vps$plot)

grid.text(rr$rarity,x = unit(meme, "native"),y=unit(-1, "lines"),rot=50)

popViewport(3)

distribution of “Battlecry” to “Nothing”

#pie chart
Attackk<-data%>%arrange(attack)
Attack<-unique(Attackk%>%group_by(attack)%>%mutate(n=n())%>%ungroup()%>%select(attack,n))
lbls<-Attack$attack
slices<-Attack$n
pct <- round(slices/sum(slices)*100)
lbls <- paste(lbls, pct) # add percents to labels 
lbls <- paste(lbls,"%",sep="") # ad % to labels 
pie(slices,labels = lbls, col=rainbow(length(lbls)),
    main="Pie Chart of Attack")

#histogram
x <- Attackk$attack
h<-hist(x, breaks=12, col="red", ylim=c(0,120),xlab="deal damage to the opponent", 
    main="Histogram for attack") 
xfit<-seq(min(x),max(x),length=40) 
yfit<-dnorm(xfit,mean=mean(x),sd=sd(x)) 
yfit <- yfit*diff(h$mids[1:2])*length(x) 
lines(xfit, yfit, col="blue", lwd=2)

#density plot
d <- density(Attackk$attack)
plot(d, main="Kernel density for attack")
polygon(d, col="red", border="blue")

#list<-c("Battlecry","Taunt","HealTarget","Charge","Aura","AdjacentBuff","Spell_Damage","Freeze","Enrage","Divine_Shield","Stealth","Overload","Deathrattle","Windfury","Combo","Poisonous","Inspire","Normal","Choice","Conditional","Add","Cast","Deal","Destroy","Discover","Draw","Discard","Gain","Give","Reduce","Remove","Restore")

for(i in 11:length(data)){
  #i <- 11
  object=.dots=as.name(colnames(data)[i])
  list=as.vector(table(data[,i]))
  value<-c(0,1)
  table<-t(rbind(value,list))
#pie chart  
  lbls<-table[,1]  
  slices<-table[,2]
  pct <- round(slices/sum(slices)*100)
  lbls <- paste(lbls, pct) # add percents to labels 
  lbls <- paste(lbls,"%",sep="") # ad % to labels 
  pie(slices,labels = lbls, col=rainbow(length(lbls)),main=paste("Pie chart of",object))
  
#histogram
#  x <- lbls
#  h<-hist(x, breaks=5, col="blue", ylim=c(0,100), main=paste("Histogram for",object)) 
#  xfit<-seq(min(x),max(x),length=40) 
#  yfit<-dnorm(xfit,mean=mean(x),sd=sd(x)) 
#  yfit <- yfit*diff(h$mids[1:2])*length(x) 
#  lines(xfit, yfit, col="blue", lwd=2)

}